LLM-based Natural Language Processing (NLP) System
(Redirected from LLM-based NLP system)
Jump to navigation
Jump to search
An LLM-based Natural Language Processing (NLP) System is an NLP system that is an LLM-based system (which critically relies on a large language model).
- Example(s):
- See: LLM-Supported Clinical Trial System.
References
2023
- chat
- Q: Create a wiki table with 3 columns: "NLP Task Type", "Specific Benchmark Tasks", and "Pure LLM Solution?". In the first column, list 14 NLP task types. In the second column, list some specific benchmark tasks typically used to evaluate performance on each task type. In the third column, indicate whether a pure LLM can typically solve the task or if additional training and optimization may be required. Mark up each technical term or noun phrase using wiki link double square bracket annotation. Reply in a formatted text box.
- A:
2022
- (Wei, Tay et al., 2022) ⇒ Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.. (2022). “Emergent Abilities of Large Language Models.” In: Transactions on Machine Learning Research, 08/2022 (TMLR).
- (Srivastava et al., 2022) ⇒ Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, and others. (2022). “Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models.” In: arXiv preprint arXiv:2206.04615.